About MCP Server for Running E2E Tests
Limetest is an end-to-end testing framework for teams that want to define tests in natural language and run them with AI, including in CI workflows. It uses Playwright snapshots and can fall back to vision mode for more complex scenarios.
Key features
- 01Natural-language test cases
- 02AI-executed end-to-end tests
- 03Playwright snapshot-based testing
- 04Vision-mode fallback
- 05Headless CI test runs
Use cases
- 01Run AI-planned end-to-end tests in CI
- 02Validate AI-generated code in a browser
- 03Use vision mode when snapshot testing fails
MCP support
The Limetest MCP server uses Playwright to provide end-to-end testing for MCP clients. Its end-to-end mode requires an OpenAI API key.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMELimetest
Limetest is the most light weight end to end testing framework with AI capabilities that can run in your CI workflows. Define your test cases in natural language and let AI handle the execution.
Key Features
- Optimized for AI: Define your test cases in plain language and let AI execute them end to end.
- Lightweight & Efficient: Leverages Playwright snapshot instead of pixel analysis for faster, more reliable execution.
- Vision Capabilities: Falls back to vision mode when snapshot mode fails during more sophisticated test scenarios.
Installation
npm install @limetest/limetest
npx playwright install
User data directory
limtest will launch Chrome browser with the new profile, located at
- `%USERPROFILE%\AppData\Local\ms-limetest\mcp-chrome-profile` on Windows
- `~/Library/Caches/ms-limetest/mcp-chrome-profile` on macOS
- `~/.cache/ms-limetest/mcp-chrome-profile` on Linux
Usage
Run Tests
Use --headless for running tests headlessly in CI workflows
npx limetest example
limetest MCP Server
https://github.com/user-attachments/assets/b801f239-dc66-4b3b-bcf2-42e2a9a68721
A Model Context Protocol (MCP) server powered by Playwright that streamlinse end to end testing for your MCP client.
Use Cases
- Automated testing planned and executed by LLMs
Example config
After cloning this repo, build and add the E2E MCP server to your MCP Client as such: Notice that you need OpenAI API key to run this MCP server in end to end mode.
npm install @limetest/mcp
npx playwright install
Then:
{
"mcpServers": {
"limetest": {
"command": "npx",
"args": [
"npx @limetest/mcp",
"--api-key=<your openai api key>"
]
}
}
}
All the logged in information will be stored in that profile, you can delete it between sessions if you'd like to clear the offline state.
Acknowledgements
Limetest is based on Microsoft's Playwright MCP and optimized for automated end-to-end testing as a standalone framework. This project is distributed under the Apache 2.0 License.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.